International Journal of Computer Science & Engineering Survey (IJCSES) Vol.5, No.2, April 2014 DOI : 10.5121/ijcses.2014.5203 27 A Study of Techniques for Facial Detection and E xpression Classification G.Hemalatha 1 , C.P. Sumathi 2 1 Research Scholar, Manonmaniam Sundaranar University, Tirunelveli, India 2 Department of Computer Science, SDNB Vaishnav College For Women, Chennai, India ABSTRACT Automatic recognition of facial expressions is an important component for human-machine interfaces. It has lot of attraction in research area since 1990's.Although humans recognize face without effort or delay, recognition by a machine is still a challenge. Some of its challenges are highly dynamic in their orientation, lightening, scale, facial expression and occlusion. Applications are in the fields like user authentication, person identification, video surveillance, information security, data privacy etc. The various approaches for facial recognition are categorized into two namely holistic based facial recognition and feature based facial recognition. Holistic based treat the image data as one entity without isolating different region in the face where as feature based methods identify certain points on the face such as eyes, nose and mouth etc. In this paper, facial expression recognition is analyzed with various methods of facial detection,facial feature extraction and classification. KEYWORDS Face detection,, Feature extraction ,Machine learning ,Classification, Expression recognition. 1. INTRODUCTION Emotion is a state of feeling like thoughts, psychological changes and expressions. Emotions positively affects intelligent functions such as decision making, perception and empathic understanding according to Beeahara et.al's[1].The approach on Facial Action Coding System (FACS) which separates the expression into upper and lower face action. FACS was developed by EKMAN [2] for facial expression description. Facial expression recognition involves three steps face detection, feature extraction and expression classification. Figure1. Steps involved in Facial Detection and Expression Classification 2. FACE DETECTION The first step in face detection is preprocessing. The reason is to obtain pure facial images with normalized intensity, uniform size and shape. The steps involved in converting a image to a normalized pure facial image for feature extraction is detecting feature points, rotating to line up, Face Detection Feature Extraction Expression Classification